Analytics Goes Social

Observing behaviors using Social Network Analysis allows views that may alter the way we think and touch on deeper realities about what we need to do to protect customers.

The financial services industry remains under continuing pressure to increase operating efficiency through better utilization of data. At the same time, the industry must also manage a wide range of risks. What to do?  Many are now exploring the use of Social Network Analysis (SNA) to drive better intelligence out of networked data to avert fraud.

Ellen Joyner Roberson is Global Banking Marketing Manager for SAS and says SAS® Social Network Analysis is a powerful tool for understanding the structure of social and organizational networks. Also known as Link Analysis, SNA is the mapping and measuring of relationships and flows between people, groups, organizations, computers or other information and knowledge processing entities. The nodes in the network are the people and groups while the links show relationships or flows between the nodes. SNA provides both a visual and a mathematical analysis of complex human systems. This analytic approach has practical importance because SNA tools combine data extraction, manipulation, analytic and visualization tools to distill massive databases into a visual representation of any unusual set of linkages. In short, it analyzes and presents data that contains information such as “who knows whom,” “who calls whom,” and “who does business with whom.”

Formation of a fraud ring or "Bust-out" fraud

Turbulent credit markets, a downturn in the economy and the rise of organized crime have all resulted in a sharper focus on new ways to fight financial crimes. In this new environment, we are seeing a new criminal who is immune to conventional risk scoring. Traditional data and record-matching techniques struggle with poor data quality, missing data and many times miss or delay discovering deliberate attempts by criminals to hide identities. Legacy systems mostly resort to inexact or fuzzy matching, but this tends to generate a significant number of false matches.

Traditional approaches have inhibited the ability to visualize how relationships are taking place. By monitoring the communication patterns between network nodes, its structure  can be established. Identifying the structure of an insurgent network enables identification of critical nodes and their r elationships. However, this analysis is only half the battle. Predictive analysis is impossible without understanding the "pattern of life" within the network. Together, network analysis and predictive analysis enables financial institutions with the ability to identify the network, determine critical targets and predict when and where targets may take advantage of an opportunity.

Roberson noted examples of first-party fraud and bust-out fraud as a growing area of loss for banks. These are not just typical bad credit debt. Many are establishing accounts for the sole purpose of committing fraud. According to Roberson,  that information is going undetected by standard rules-based systems. This could go on for years, without a solution such as SNA. This solution provides a unique network visualization that enables investigators to actually see connection points so that they can uncover previously unknown relationships and conduct more effective investigations.

Alert Details and Comparisons

Analyzing social relationships could be particularly useful in combating organized crime rings. SNA uncovers connections that better assist investigators and analysts in producing actionable intelligence. Using this technique can expose fraud faster, identify indirect crime and deceptive patterns, and leverage information linking fraudsters to illegal activities. The more sophisticated fraud rings may not be detected right away by looking only at individual transactions. Conventional systems typically fall into that category and only use rules-based analysis. But, by integrating advanced analytics with existing business rules, end users can incorporate a different dynamic of analytical business rules and anomalies such as clustering analysis, mean and standard deviation, data mining and other predictive analysis to have one powerful ally in fraud prediction and protection. By leveraging this hybrid approach to network analysis, banks can optimize their existing investment and evolve their detection process to incorporate more intelligence and refine the alert monitoring and detection process.

SNA methods in the context of an ongoing fraud or criminal investigation can eliminate antiquated guesswork and ad hoc reporting. While those methods can be economical, it does not provide the flexibility to follow a trail of links that may not be immediately apparent. An interactive reporting system enables investigators and analysts to query data and search for interesting or unusual connections. Overall, SNA can and will reduce the time to detect fraudulent situations while automating the investigation time-to-resolution as companies utilize the ability to pick up on subtle and illegal behaviors that have typically gone undetected.

SAS will introduce their SNA solution in April 2009 to banking, insurance, health care and government. There are not many vendors who offer this technology, and SAS’s platform approach provides enhanced fraud detection, greater insight into SAR management responsibilities and improved operational efficiency while decreasing fraud spending.

SAS® Fraud Framework delivers a technology infrastructure for preventing, detecting and managing financial crimes across the various lines of business. The platform marries the three components of detection, alert management and case management, while providing category specific workflow, content management and advanced analytics. These components are fully integrated with SNA and offer both top down and bottom up functionality in making hidden and risky networks more visible.  Advanced, large-scale network analytics work across internal and external data sources to link customers and accounts based on common attributes or more subtle patterns of behavior. By integrating SNA into the entire fraud framework process, previously undiscovered alerts and flags can be fed back into the alert monitoring process for fine-tuning the ability to detect fraud. And, it can be integrated into the fraud framework SAS already delivers, or it can be implemented into an organization’s existing infrastructure.

While social network analysis has been present in some form or another for decades, taking the concept to fraud prevention is where leading-edge companies will make their mark in the coming years. SNA is a tool with great potential and hits on a profound truth about the way humans interact. Observing behaviors through SNA allows views that may alter the way we think and touch on deeper realities about what we need to do to protect customers.

Ellen Joyner Roberson, SAS Global Banking Marketing Manager